Predictive Sampling with Forecasting Autoregressive Models

Understand

Autoregressive models (ARMs) currently hold state-of-the-art performance in likelihood-based modeling of image and audio data.

• Generally, neural network based ARMs are designed to allow fast inference, but sampling from these models is impractically slow.
• In this paper, we introduce the predictive sampling algorithm: a procedure that exploits the fast inference property of ARMs in order to speed up sampling, while keeping the model intact.
• We propose two variations of predictive sampling, namely sampling with ARM fixed-point iteration and learned forecasting modules.